io.github.hanzohanzhe/grandet

Est-ce que io.github.hanzohanzhe/grandet est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.hanzohanzhe/grandet » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 6 outils

• grandet_find_cheapest_api≈ 1548 tokens

  Compare Grandet model prices within each unit. Read listings for price-only ordering and conditions; legacy recommended/alternative/cheapest retain their old meanings. Use view=compact for shared connection cards and a short text response. Provide exactly one model or name selector. host records the source only and never selects the inference route. Send targetApp when the user or conversation identifies the intended API application, including explicit use in the current app. With no target, compare directly. An unrecorded app connection permits a price-only recommendation, not a compatibility claim. Omit profile/protocol for a multi-protocol app unless already specified. Existing client remains a legacy target-app alias. Infer coding/chat/long_output from the task; presets are estimates. Use grandet_list_apps only when application facts are needed. Do not request API keys.

  Paramètres, retour & exemple (19)

  Paramètres

  • os · string · optionnel · windows | macos | linux | unknown
    Operating system the target app runs on, for connection steps: windows, macos, linux or unknown.
  • mix · string · optionnel
    Workload used to blend input, cache and output prices into one price per million total tokens. Presets "chat" (default), "coding" and "long_output", or custom input/cache-read/output/cache-write shares totalling 100.
  • asOf · string · optionnel
    Evaluate as of this UTC time (ISO 8601, e.g. "2026-10-16T12:00:00Z"). Omit to evaluate now.
  • host · string · optionnel
    The assistant or app making this call, e.g. "claude-code" or "codex". Attribution only; it does not change results.
  • lang · string · optionnel · en | zh-CN
    Answer language: "en" or "zh-CN".
  • name · string · optionnel
    The catalogue's 20-character hexadecimal raw-name ID (not the name text). Send exactly one of model or name.
  • view · string · optionnel · full | compact | brief
    "compact" (default): a short text summary plus the listings, with connection cards shared in integrationCards; about a third of the size. "full": every legacy field, with the whole JSON repeated as text.
  • limit · integer · optionnel
    Rows per block, 1–20 (default 5).
  • model · string · optionnel
    Model to look up: a catalogue ID, an exact model name or a natural name such as "claude-sonnet-5-5". Send exactly one of model or name. An ambiguous name returns NEEDS_CLARIFICATION with candidates.
  • plans · string · optionnel · best | all
    "best" (default) keeps one group per site; "all" lists every group of every site.
  • client · string · optionnel
    Legacy alias of targetApp. Prefer targetApp.
  • channel · string · optionnel · standard | declared-nonstandard | all
    "standard" (default) lists ordinary channels, "declared-nonstandard" only channels the site itself labels nonstandard, "all" both.
  • currency · string · optionnel · USD_CREDIT | CNY_CREDIT | USD | CNY
    Limit to one unit board: USD_CREDIT or CNY_CREDIT (site credit, not cash), USD or CNY (cash). Never compare prices across units.
  • targetApp · string · optionnel
    Catalogue ID of the app that will use the API, e.g. "openclaw", "claude-code" or "codex". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.
  • releaseSet · string · optionnel
    Pin a published data release by its release-set hash. Omit to use the current release.
  • skillBuild · string · optionnel
    Grandet Skill build ID when called from the Skill. Omit otherwise.
  • endpointType · string · optionnel · openai | openai-response | anthropic | gemini
    Limit to one API protocol. Send it only when the user named a protocol.
  • skillVersion · string · optionnel
    Grandet Skill version when called from the Skill, e.g. "0.3.0". Omit otherwise.
  • targetProfile · string · optionnel
    An inference profile ID of the target app (see grandet_list_apps). Only together with targetApp or client.

  Exemple d'appel

  {"name": "grandet_find_cheapest_api", "arguments": {"os": "windows", "mix": "texte", "asOf": "texte", "host": "texte", "lang": "en", "name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"help": {}, "scope": {}, "boards": [], "schema": "texte", "coverage": {}}}

• grandet_find_free_credits≈ 819 tokens

  Find current official free tiers, application-based credits and relay free groups. Return the stated benefit, six requirements, deadline, original observation and claim link. userCanMeet=no_card excludes explicit required/conditional card entries; unknown card requirements remain clearly labelled unknown. Application categories describe programs, not the user’s eligibility. Follow pagination.

  Paramètres, retour & exemple (13)

  Paramètres

  • q · string · optionnel
    Model, vendor or site to search, e.g. "gemini".
  • asOf · string · optionnel
    Evaluate as of this UTC time (ISO 8601, e.g. "2026-10-16T12:00:00Z"). Omit to evaluate now.
  • host · string · optionnel
    The assistant or app making this call, e.g. "claude-code" or "codex". Attribution only; it does not change results.
  • kind · string · optionnel · official | relay | all
    "official" free tiers and credits, "relay" free groups, or "all".
  • lang · string · optionnel · en | zh-CN
    Answer language: "en" or "zh-CN".
  • page · integer · optionnel
    Result page, starting at 1.
  • view · string · optionnel · full | compact
    "compact" (default): about 18 KB for a typical query. "full": every field, often over 250 KB.
  • limit · integer · optionnel
    Results per page, 1–20.
  • targetApp · string · optionnel
    Catalogue ID of the app that will use the API, e.g. "openclaw", "claude-code" or "codex". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.
  • releaseSet · string · optionnel
    Pin a published data release by its release-set hash. Omit to use the current release.
  • skillBuild · string · optionnel
    Grandet Skill build ID when called from the Skill. Omit otherwise.
  • userCanMeet · string · optionnel · any | no_card | student
    Only offers the user can meet: "any", "no_card" (no payment card) or "student".
  • skillVersion · string · optionnel
    Grandet Skill version when called from the Skill, e.g. "0.3.0". Omit otherwise.

  Exemple d'appel

  {"name": "grandet_find_free_credits", "arguments": {"q": "texte", "asOf": "texte", "host": "texte", "kind": "official", "lang": "en", "page": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"help": {}, "total": 1, "offers": [], "schema": "texte", "coverage": {}, "qualification": {}}}

• grandet_glossary≈ 610 tokens

  Look up the published Grandet relay glossary. Site labels are source claims and glossary terms explain them; they do not verify quality. Query q or category and follow pagination. Unknown terms include up to three related FAQ links.

  Paramètres, retour & exemple (9)

  Paramètres

  • q · string · optionnel
    Term or phrase to look up, e.g. "倍率" or "token group".
  • host · string · optionnel
    The assistant or app making this call, e.g. "claude-code" or "codex". Attribution only; it does not change results.
  • lang · string · optionnel · en | zh-CN
    Answer language: "en" or "zh-CN".
  • page · integer · optionnel
    Result page, starting at 1.
  • limit · integer · optionnel
    Results per page, 1–20.
  • category · string · optionnel
    Limit to one glossary category.
  • targetApp · string · optionnel
    Catalogue ID of the app that will use the API, e.g. "openclaw", "claude-code" or "codex". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.
  • skillBuild · string · optionnel
    Grandet Skill build ID when called from the Skill. Omit otherwise.
  • skillVersion · string · optionnel
    Grandet Skill version when called from the Skill, e.g. "0.3.0". Omit otherwise.

  Exemple d'appel

  {"name": "grandet_glossary", "arguments": {"q": "texte", "host": "texte", "lang": "en", "page": 1, "limit": 1, "category": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"faq": [], "terms": [], "schema": "texte", "pagination": {}, "suggestions": []}}

• grandet_list_apps≈ 483 tokens

  Read the shared Grandet application list and inference profiles before selecting a supplier. App profiles determine API compatibility; MCP capability alone does not prove an inference route or Skill installation. Use only when the target app ID, supported protocol or configuration variant is uncertain.

  Paramètres, retour & exemple (6)

  Paramètres

  • app · string · optionnel
    Catalogue app ID to show, e.g. "openclaw". Omit to list every app.
  • host · string · optionnel
    The assistant or app making this call, e.g. "claude-code" or "codex". Attribution only; it does not change results.
  • lang · string · optionnel · en | zh-CN
    Answer language: "en" or "zh-CN".
  • targetApp · string · optionnel
    Catalogue ID of the app that will use the API, e.g. "openclaw", "claude-code" or "codex". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.
  • skillBuild · string · optionnel
    Grandet Skill build ID when called from the Skill. Omit otherwise.
  • skillVersion · string · optionnel
    Grandet Skill version when called from the Skill, e.g. "0.3.0". Omit otherwise.

  Exemple d'appel

  {"name": "grandet_list_apps", "arguments": {"app": "texte", "host": "texte", "lang": "en", "targetApp": "texte", "skillBuild": "texte", "skillVersion": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"apps": [], "schema": "texte"}}

• grandet_quote_evidence≈ 789 tokens

  Read one provider's paged public declarations for a model and optional rowId. Use only when a detail matters, not before every recommendation. A missing row on one page is not proof of absence; follow pagination if needed. This does not test model quality or spend money.

  Paramètres, retour & exemple (12)

  Paramètres

  • asOf · string · optionnel
    Evaluate as of this UTC time (ISO 8601, e.g. "2026-10-16T12:00:00Z"). Omit to evaluate now.
  • host · string · optionnel
    The assistant or app making this call, e.g. "claude-code" or "codex". Attribution only; it does not change results.
  • lang · string · optionnel · en | zh-CN
    Answer language: "en" or "zh-CN".
  • name · string · optionnel
    The catalogue's 20-character hexadecimal raw-name ID (not the name text). Send exactly one of model or name.
  • model · string · optionnel
    Model to look up: a catalogue ID, an exact model name or a natural name such as "claude-sonnet-5-5". Send exactly one of model or name. An ambiguous name returns NEEDS_CLARIFICATION with candidates.
  • rowId · string · optionnel
    The rowId of the selected row, to read that exact declaration.
  • provider · string · requis
    The sourceId of the row to inspect (the site host, e.g. "api.example.com"), not the operator ID.
  • offerPage · integer · optionnel
    Page of this provider's declarations, starting at 1. Follow it when rowId is absent.
  • targetApp · string · optionnel
    Catalogue ID of the app that will use the API, e.g. "openclaw", "claude-code" or "codex". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.
  • releaseSet · string · optionnel
    Pin a published data release by its release-set hash. Omit to use the current release.
  • skillBuild · string · optionnel
    Grandet Skill build ID when called from the Skill. Omit otherwise.
  • skillVersion · string · optionnel
    Grandet Skill version when called from the Skill, e.g. "0.3.0". Omit otherwise.

  Exemple d'appel

  {"name": "grandet_quote_evidence", "arguments": {"provider": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"rows": [], "schema": "texte", "pagination": {}, "websiteUrl": "texte"}}

• grandet_resolve_model≈ 576 tokens

  Look up public model identifiers when a requested name is ambiguous. Results are a page of candidates, not a cheapest-provider ranking. Prefer an exact officialId match; do not silently substitute a different model generation.

  Paramètres, retour & exemple (7)

  Paramètres

  • host · string · optionnel
    The assistant or app making this call, e.g. "claude-code" or "codex". Attribution only; it does not change results.
  • lang · string · optionnel · en | zh-CN
    Answer language: "en" or "zh-CN".
  • name · string · requis
    Model name text to look up, e.g. "sonnet" or "deepseek v4".
  • page · integer · optionnel
    Result page, starting at 1.
  • targetApp · string · optionnel
    Catalogue ID of the app that will use the API, e.g. "openclaw", "claude-code" or "codex". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.
  • skillBuild · string · optionnel
    Grandet Skill build ID when called from the Skill. Omit otherwise.
  • skillVersion · string · optionnel
    Grandet Skill version when called from the Skill, e.g. "0.3.0". Omit otherwise.

  Exemple d'appel

  {"name": "grandet_resolve_model", "arguments": {"name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"help": {}, "schema": "texte", "status": "texte", "candidates": [], "pagination": {}}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://grandet.ai/mcp